Maximum entropy models are a common modeling technique, but prone to overfitting. We show that using an exponential distribution as a prior leads to bounded absolute discounting b...
We consider the problem of learning multiscale graphical models. Given a collection of variables along with covariance specifications for these variables, we introduce hidden var...
Myung Jin Choi, Venkat Chandrasekaran, Alan S. Wil...
In blind source separation (BSS), two di erent separation techniques are mainly used: minimal mutual information (MMI), where minimization of the mutual output information yields ...
Fabian J. Theis, Christoph Bauer, Elmar Wolfgang L...
In this paper we will present a maximum entropy filter for the translation rules of a statistical machine translation system based on tree transducers. This filter can be success...
We regard answer extraction of Question Answering (QA) system as a classification problem, classifying answer candidate sentences into positive or negative. To confirm the feasibil...